Computing Approximately, and Efficiently
Swagath Venkataramani1,a, Srimat T. Chakradhar2, Kaushik Roy1,b and Anand Raghunathan1,c
1School of Electrical and Computer Engineering, Purdue University, USA.
2Systems Architecture Department, NEC Laboratories America, USA.
Recent years have witnessed significant interest in
the area of approximate computing. Much of this interest stems
from the quest for new sources of computing efficiency in the
face of diminishing benefits from technology scaling. We argue
that trends in computing workloads will greatly increase the
opportunities for approximate computing, describe the vision
and key principles that have guided our work in this area, and
outline a range of approximate computing techniques that we
have developed at all layers of the computing stack, spanning
circuits, architecture, and software.
Full Text (PDF)